AI Agents news and analysis on Web Pulse: 49335 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
A developer released Web-MCP-Bridge, an open-source browser extension paired with a local Python WebSocket bridge that lets web-based AI chat interfaces such as ChatGPT, Gemini, Claude and DeepSeek execute local Model Co…
DeepSeek open-sourced dsh-superagent on October 31 under an MIT license, a research prototype coding agent that watches a GitHub repository, picks up authorized bug reports, writes a fix in an isolated Worker session, an…
Open-source desktop app Strata lets users run AI models locally for chat, coding and image work without an account or an expensive GPU, serving models through local OpenAI- and Anthropic-compatible APIs that support Clau…
PagerDuty introduced Paige, an SRE agent built on more than 16 years of operational data, on November 3, 2026, to detect, remediate and prevent incidents inside the PD Reliability Platform. Paige consolidates alerts and …
PagerDuty announced Paige, an SRE agent that joins on-call rotations and works incidents alongside engineers, handling diagnostics, coordinating responders in Slack and Zoom, and drafting post-incident reviews, with guar…
Towards Data Science published a tutorial on three techniques for developers to understand their codebase when coding agents write the code: writing feature memos, reviewing pull requests, and building visual HTML explai…
An independent pentest by security firm Astra found 30 confirmed vulnerabilities, including 13 critical authentication and authorization issues, in a single Base44 app built from a security-explicit prompt during Q2 2026…
CrowdStrike reported that the China-linked group VAPOR PANDA used an AI-powered penetration testing framework called ARTEX to target more than 200 organizations across at least 14 countries in an 11-day campaign beginnin…
A preprint paper by MIT economist Stephen Morris and colleagues from Yale and Columbia proposes "reverse game theory," or mechanism design, as an alternative to interpretability and value-training approaches for keeping …
A developer has announced Dagento, a self-built local AI agent framework written in PHP for Linux, intended to address setup difficulty and reliability problems the developer encountered in Hermes Agent, OpenClaw and Age…
The DeepSeek Harness team published a paper, "Exploring Super-agent Design," describing the architecture behind its internal always-on agent, which monitors team chat, spots untagged bugs, and opens pull requests to fix …
A free, open-source course called AI Red Team Academy has been released, offering 60–80 hours of offensive security training across 8 modules on attacking LLMs, RAG pipelines, multi-agent systems, and ML supply chains. E…
CrowdStrike announced at Fal.Con Europe 2026 that it has brought its Falcon Guardian sensor natively inside Anthropic's Claude Cowork virtual machine, giving endpoint security visibility into the processes, packages and …
A developer published a workaround that lets Claude Code trigger its own /compact command, since the tool cannot invoke it internally. A rule added to CLAUDE.md has Claude run a compact-self script as its final action, a…
Google released the google-cloud-developer plugin for the Antigravity Marketplace on November 2, 2026, installable via `agy plugin install google-cloud-developer`, to connect cloud-management capabilities to agentic work…
A new study examines whether coding agents can undergo continual harness self-evolution without forgetting previously learned capabilities, focusing on approaches that improve agent performance without modifying the foun…
CrowdStrike announced at Fal.Con EU 2026 its intent to acquire Dreadnode, bringing automated AI security testing to the CrowdStrike Falcon platform, with Dreadnode generally available in Q4 FY27. Dreadnode runs more than…
CrowdStrike introduced AI Kill Switch in CrowdStrike Falcon Guardian, a control that directs connected AI gateways to block access to the AI models powering agents' decisions and actions. The Falcon AI Gateway is now gen…
CrowdStrike unveiled new AI detection and response (AIDR) capabilities for Falcon Guardian at Fal.Con Europe 2026, including a new AI kill switch that lets security teams cut off AI model access at AI gateways when agent…
An OpenAI model, Astra, running through OpenAI's Codex environment, scored 49 out of 50 (98%) on the 50-problem TheoPhysEval theoretical physics benchmark after researchers from Harvard, the University of Texas and Googl…